{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:11Z","timestamp":1786120811554,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62372314"],"award-info":[{"award-number":["62372314"]}]},{"name":"NSFC\/RGC Joint Research Scheme","award":["N_PolyU5179\/25"],"award-info":[{"award-number":["N_PolyU5179\/25"]}]},{"name":"Robotic AI-Scientist platform of Chinese Academy of Sciences","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project","award":["2025ZD0121802"],"award-info":[{"award-number":["2025ZD0121802"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818854","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"12291-12302","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Chem-R: Learning to Reason as a Chemist"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5893-525X","authenticated-orcid":false,"given":"Weida","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9813-923X","authenticated-orcid":false,"given":"Benteng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3374-7871","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2306-844X","authenticated-orcid":false,"given":"Wanhao","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5928-6272","authenticated-orcid":false,"given":"Ben","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2926-1371","authenticated-orcid":false,"given":"Shuchen","family":"Pu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3021-4523","authenticated-orcid":false,"given":"Shuzhou","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-7733","authenticated-orcid":false,"given":"Jin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6537-1924","authenticated-orcid":false,"given":"Tianshu","family":"Yu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-5177","authenticated-orcid":false,"given":"Xiao-Yong","family":"Wei","sequence":"additional","affiliation":[{"name":"PolyU HK, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7705-2296","authenticated-orcid":false,"given":"Jiatong","family":"Li","sequence":"additional","affiliation":[{"name":"PolyU HK, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2909-2407","authenticated-orcid":false,"given":"Zifu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6756-6154","authenticated-orcid":false,"given":"Yuqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4614-4718","authenticated-orcid":false,"given":"Shufei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Chain-of-thought reasoning in the wild is not always faithful. arXiv preprint arXiv:2503.08679","author":"Arcuschin Iv\u00e1n","year":"2025","unstructured":"Iv\u00e1n Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, and Arthur Conmy. 2025. Chain-of-thought reasoning in the wild is not always faithful. arXiv preprint arXiv:2503.08679 (2025)."},{"key":"e_1_3_2_1_2_1","unstructured":"Lei Bai Zhongrui Cai Maosong Cao Weihan Cao Chiyu Chen Haojiong Chen Kai Chen Pengcheng Chen Ying Chen Yongkang Chen et al. 2025. Intern-s1: A scientific multimodal foundation model. arXiv preprint arXiv:2508.15763 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Monitoring reasoning models for misbehavior and the risks of promoting obfuscation. arXiv preprint arXiv:2503.11926","author":"Baker Bowen","year":"2025","unstructured":"Bowen Baker, Joost Huizinga, Leo Gao, Zehao Dou, Melody Y Guan, Aleksander Madry, Wojciech Zaremba, Jakub Pachocki, and David Farhi. 2025. Monitoring reasoning models for misbehavior and the risks of promoting obfuscation. arXiv preprint arXiv:2503.11926 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation. arXiv preprint arXiv:2503.08537","author":"Bran Andres M","year":"2025","unstructured":"Andres M Bran, Theo A Neukomm, Daniel P Armstrong, Zlatko Jon\u010dev, and Philippe Schwaller. 2025. Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation. arXiv preprint arXiv:2503.08537 (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"Instructmol: Multi-modal integration for building a versatile and reliable molecular assistant in drug discovery. arXiv preprint arXiv:2311.16208","author":"Cao He","year":"2023","unstructured":"He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, and Yu Li. 2023. Instructmol: Multi-modal integration for building a versatile and reliable molecular assistant in drug discovery. arXiv preprint arXiv:2311.16208 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"V23, 5","author":"Cao Yi","year":"2022","unstructured":"Yi Cao, Zhen-Qun Yang, Xu-Lu Zhang, Wenqi Fan, Yaowei Wang, Jiajun Shen, Dong-Qing Wei, Qing Li, and Xiao-Yong Wei. 2022. Identifying the kind behind SMILES\u2014anatomical therapeutic chemical classification using structure-only representations. Briefings in Bioinformatics, V23, 5 (2022), bbac346."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci025531g"},{"key":"e_1_3_2_1_8_1","unstructured":"Yanda Chen Joe Benton Ansh Radhakrishnan Jonathan Uesato Carson Denison John Schulman Arushi Somani Peter Hase Misha Wagner Fabien Roger et al. 2025. Reasoning Models Don't Always Say What They Think. arXiv preprint arXiv:2505.05410 (2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"V3, 5","author":"Coley Connor W","year":"2017","unstructured":"Connor W Coley, Regina Barzilay, Tommi S Jaakkola, William H Green, and Klavs F Jensen. 2017. Prediction of organic reaction outcomes using machine learning. ACS central science, V3, 5 (2017), 434-443."},{"key":"e_1_3_2_1_10_1","unstructured":"Google DeepMind. 2025. Gemini 3 Pro Model Card. https:\/\/storage.googleapis.com\/deepmind-media\/Model-Cards\/Gemini-3-Pro-Model-Card.pdf"},{"key":"e_1_3_2_1_11_1","volume-title":"Forty-first International Conference on Machine Learning","author":"Du Yilun","year":"2023","unstructured":"Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. Forty-first International Conference on Machine Learning (2023)."},{"key":"e_1_3_2_1_12_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_13_1","volume-title":"Translation between molecules and natural language. arXiv preprint arXiv:2204.11817","author":"Edwards Carl","year":"2022","unstructured":"Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. 2022. Translation between molecules and natural language. arXiv preprint arXiv:2204.11817 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars. arXiv preprint arXiv:2503.01307","author":"Gandhi Kanishk","year":"2025","unstructured":"Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, and Noah D Goodman. 2025. Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars. arXiv preprint arXiv:2503.01307 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00472-1"},{"key":"e_1_3_2_1_16_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Taicheng Guo Bozhao Nan Zhenwen Liang Zhichun Guo Nitesh Chawla Olaf Wiest Xiangliang Zhang et al. 2023. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. Advances in Neural Information Processing Systems V36 (2023) 59662-59688.","DOI":"10.52202\/075280-2607"},{"key":"e_1_3_2_1_18_1","volume-title":"V3, 1","author":"Hatakeyama-Sato Kan","year":"2023","unstructured":"Kan Hatakeyama-Sato, Naoki Yamane, Yasuhiko Igarashi, Yuta Nabae, and Teruaki Hayakawa. 2023. Prompt engineering of GPT-4 for chemical research: what can\/cannot be done? Science and Technology of Advanced Materials: Methods, V3, 1 (2023), 2260300."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop: a machine learning package for chemical property prediction","volume":"64","author":"Heid Esther","year":"2023","unstructured":"Esther Heid, Kevin P Greenman, Yunsie Chung, Shih-Cheng Li, David E Graff, Florence H Vermeire, Haoyang Wu, William H Green, and Charles J McGill. 2023. Chemprop: a machine learning package for chemical property prediction. Journal of Chemical Information and Modeling, V64, 1 (2023), 9-17.","journal-title":"Journal of Chemical Information and Modeling"},{"key":"e_1_3_2_1_20_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"V3, 1","author":"Irwin Ross","year":"2022","unstructured":"Ross Irwin, Spyridon Dimitriadis, Jiazhen He, and Esben Jannik Bjerrum. 2022. Chemformer: a pre-trained transformer for computational chemistry. Machine Learning: Science and Technology, V3, 1 (2022), 015022."},{"key":"e_1_3_2_1_22_1","volume-title":"Chem3dllm: 3d multimodal large language models for chemistry. arXiv preprint arXiv:2508.10696","author":"Jiang Lei","year":"2025","unstructured":"Lei Jiang, Shuzhou Sun, Biqing Qi, Yuchen Fu, Xiaohua Xu, Yuqiang Li, Dongzhan Zhou, and Tianfan Fu. 2025. Chem3dllm: 3d multimodal large language models for chemistry. arXiv preprint arXiv:2508.10696 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Prover-verifier games improve legibility of llm outputs. arXiv preprint arXiv:2407.13692","author":"Kirchner Jan Hendrik","year":"2024","unstructured":"Jan Hendrik Kirchner, Yining Chen, Harri Edwards, Jan Leike, Nat McAleese, and Yuri Burda. 2024. Prover-verifier games improve legibility of llm outputs. arXiv preprint arXiv:2407.13692 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, V35 (2022), 22199-22213."},{"key":"e_1_3_2_1_25_1","volume-title":"V76, 12","author":"Kuhn HJ","year":"2004","unstructured":"HJ Kuhn, SE Braslavsky, and R Schmidt. 2004. Chemical actinometry (IUPAC technical report). Pure and Applied Chemistry, V76, 12 (2004), 2105-2146."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00579-z"},{"key":"e_1_3_2_1_27_1","volume-title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations. arXiv preprint arXiv:2505.21318","author":"Li Hao","year":"2025","unstructured":"Hao Li, He Cao, Bin Feng, Yanjun Shao, Xiangru Tang, Zhiyuan Yan, Li Yuan, Yonghong Tian, and Yu Li. 2025a. Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations. arXiv preprint arXiv:2505.21318 (2025)."},{"key":"e_1_3_2_1_28_1","volume-title":"TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation. arXiv preprint arXiv:2412.14642","author":"Li Jiatong","year":"2024","unstructured":"Jiatong Li, Junxian Li, Yunqing Liu, Dongzhan Zhou, and Qing Li. 2024a. TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation. arXiv preprint arXiv:2412.14642 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3557697"},{"key":"e_1_3_2_1_30_1","volume-title":"Empowering molecule discovery for molecule-caption translation with large language models: A chatgpt perspective","author":"Li Jiatong","year":"2024","unstructured":"Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, and Qing Li. 2024b. Empowering molecule discovery for molecule-caption translation with large language models: A chatgpt perspective. IEEE transactions on knowledge and data engineering (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Molreflect: Towards in-context fine-grained alignments between molecules and texts","author":"Li Jiatong","year":"2026","unstructured":"Jiatong Li, Yunqing Liu, Wei Liu, Jingdi Lei, Di Zhang, Wenqi Fan, Dongzhan Zhou, Yuqiang Li, and Qing Li. 2026. Molreflect: Towards in-context fine-grained alignments between molecules and texts. IEEE Transactions on Knowledge and Data Engineering (2026)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32020"},{"key":"e_1_3_2_1_33_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman Hunter","year":"2024","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let's verify step by step. The Twelfth International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_34_1","unstructured":"Aixin Liu Aoxue Mei Bangcai Lin Bing Xue Bingxuan Wang Bingzheng Xu Bochao Wu Bowei Zhang Chaofan Lin Chen Dong et al. 2025b. Deepseek-v3. 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Statistical rejection sampling improves preference optimization. arXiv preprint arXiv:2309.06657","author":"Liu Tianqi","year":"2023","unstructured":"Tianqi Liu, Yao Zhao, Rishabh Joshi, Misha Khalman, Mohammad Saleh, Peter J Liu, and Jialu Liu. 2023c. Statistical rejection sampling improves preference optimization. arXiv preprint arXiv:2309.06657 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation. arXiv preprint arXiv:2506.01116","author":"Liu Xinyi","year":"2025","unstructured":"Xinyi Liu, Lipeng Ma, Yixuan Li, Weidong Yang, Qingyuan Zhou, Jiayi Song, Shuhao Li, and Ben Fei. 2025a. ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation. arXiv preprint arXiv:2506.01116 (2025)."},{"key":"e_1_3_2_1_37_1","volume-title":"Molca: Molecular graph-language modeling with cross-modal projector and uni-modal adapter. arXiv preprint arXiv:2310.12798","author":"Liu Zhiyuan","year":"2023","unstructured":"Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua. 2023a. Molca: Molecular graph-language modeling with cross-modal projector and uni-modal adapter. arXiv preprint arXiv:2310.12798 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Molxpt: Wrapping molecules with text for generative pre-training. arXiv preprint arXiv:2305.10688","author":"Liu Zequn","year":"2023","unstructured":"Zequn Liu, Wei Zhang, Yingce Xia, Lijun Wu, Shufang Xie, Tao Qin, Ming Zhang, and Tie-Yan Liu. 2023b. Molxpt: Wrapping molecules with text for generative pre-training. arXiv preprint arXiv:2305.10688 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"V23, 6","author":"Luo Renqian","year":"2022","unstructured":"Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics, V23, 6 (2022), bbac409."},{"key":"e_1_3_2_1_40_1","volume-title":"Llm and simulation as bilevel optimizers: A new paradigm to advance physical scientific discovery. arXiv preprint arXiv:2405.09783","author":"Ma Pingchuan","year":"2024","unstructured":"Pingchuan Ma, Tsun-Hsuan Wang, Minghao Guo, Zhiqing Sun, Joshua B Tenenbaum, Daniela Rus, Chuang Gan, and Wojciech Matusik. 2024. Llm and simulation as bilevel optimizers: A new paradigm to advance physical scientific discovery. arXiv preprint arXiv:2405.09783 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Ludovico Mitchener, Samuel G. Rodriques, and Andrew D. White.","author":"Narayanan Siddharth M.","year":"2025","unstructured":"Siddharth M. Narayanan, James D. Braza, Ryan-Rhys Griffiths, Albert Bou, Geemi P. Wellawatte, Mayk Caldas Ramos, Ludovico Mitchener, Samuel G. Rodriques, and Andrew D. White. 2025. Training a Scientific Reasoning Model for Chemistry. arXiv preprint arXiv:2506.17238 (2025)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems V35 (2022).","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_43_1","volume-title":"Structured chemistry reasoning with large language models. arXiv preprint arXiv:2311.09656","author":"Ouyang Siru","year":"2023","unstructured":"Siru Ouyang, Zhuosheng Zhang, Bing Yan, Xuan Liu, Yejin Choi, Jiawei Han, and Lianhui Qin. 2023. Structured chemistry reasoning with large language models. arXiv preprint arXiv:2311.09656 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Iterative reasoning preference optimization. Advances in Neural Information Processing Systems","author":"Pang Richard Yuanzhe","year":"2024","unstructured":"Richard Yuanzhe Pang, Weizhe Yuan, He He, Kyunghyun Cho, Sainbayar Sukhbaatar, and Jason Weston. 2024. Iterative reasoning preference optimization. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00512-4"},{"key":"e_1_3_2_1_47_1","volume-title":"ChatGPT-3.5 and humans in clinical chemistry Multiple-Choice questions. Advances in Medical Education and Practice","author":"Sallam Malik","year":"2024","unstructured":"Malik Sallam, Khaled Al-Salahat, Huda Eid, Jan Egger, and Behrus Puladi. 2024. Human versus artificial intelligence: ChatGPT-4 outperforming Bing, bard, ChatGPT-3.5 and humans in clinical chemistry Multiple-Choice questions. Advances in Medical Education and Practice (2024), 857-871."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00564"},{"key":"e_1_3_2_1_49_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"ChemMLLM: Chemical Multimodal Large Language Model. arXiv preprint arXiv:2505.16326","author":"Tan Qian","year":"2025","unstructured":"Qian Tan, Dongzhan Zhou, Peng Xia, Wanhao Liu, Wanli Ouyang, Lei Bai, Yuqiang Li, and Tianfan Fu. 2025. ChemMLLM: Chemical Multimodal Large Language Model. arXiv preprint arXiv:2505.16326 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"Galactica: A large language model for science. arXiv preprint arXiv:2211.09085","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A large language model for science. arXiv preprint arXiv:2211.09085 (2022)."},{"key":"e_1_3_2_1_52_1","unstructured":"Kimi Team Tongtong Bai Yifan Bai Yiping Bao SH Cai Yuan Cao Y Charles HS Che Cheng Chen Guanduo Chen et al. 2026. Kimi K2. 5: Visual Agentic Intelligence. arXiv preprint arXiv:2602.02276 (2026)."},{"key":"e_1_3_2_1_53_1","volume-title":"Dart-math: Difficulty-aware rejection tuning for mathematical problem-solving. Advances in Neural Information Processing Systems","author":"Tong Yuxuan","year":"2024","unstructured":"Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, and Junxian He. 2024. Dart-math: Difficulty-aware rejection tuning for mathematical problem-solving. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_3_2_1_55_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, V35 (2022), 24824-24837."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"e_1_3_2_1_57_1","volume-title":"V9, 2","author":"Wu Zhenqin","year":"2018","unstructured":"Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. 2018. MoleculeNet: a benchmark for molecular machine learning. Chemical science, V9, 2 (2018), 513-530."},{"key":"e_1_3_2_1_58_1","unstructured":"Yingce Xia Peiran Jin Shufang Xie Liang He Chuan Cao Renqian Luo Guoqing Liu Yue Wang Zequn Liu Yuan-Jyue Chen et al. 2025. Nature Language Model: Deciphering the Language of Nature for Scientific Discovery. arXiv preprint arXiv:2502.07527 (2025)."},{"key":"e_1_3_2_1_59_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_60_1","volume-title":"Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b. arXiv preprint arXiv:2406.07394","author":"Zhang Di","year":"2024","unstructured":"Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li, and Wanli Ouyang. 2024a. Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b. arXiv preprint arXiv:2406.07394 (2024)."},{"key":"e_1_3_2_1_61_1","volume-title":"Chemllm: A chemical large language model. arXiv preprint arXiv:2402.06852","author":"Zhang Di","year":"2024","unstructured":"Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Wanli Ouyang, et al., 2024b. Chemllm: A chemical large language model. arXiv preprint arXiv:2402.06852 (2024)."},{"key":"e_1_3_2_1_62_1","unstructured":"Di Zhang Weida Wang Junxian Li Xunzhi Wang Jiatong Li Jianbo Wu Jingdi Lei Haonan He Peng Ye Shufei Zhang et al. 2025d. Control-R: Towards controllable test-time scaling. arXiv preprint arXiv:2506.00189 (2025)."},{"key":"e_1_3_2_1_63_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang Lunjun","year":"2025","unstructured":"Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2025b. Generative Verifiers: Reward Modeling as Next-Token Prediction. The Thirteenth International Conference on Learning Representations (2025)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf194"},{"key":"e_1_3_2_1_65_1","unstructured":"Yu Zhang Yang Han Shuai Chen Ruijie Yu Xin Zhao Xianbin Liu Kaipeng Zeng Mengdi Yu Jidong Tian Feng Zhu et al. 2025a. Large language models to accelerate organic chemistry synthesis. Nature Machine Intelligence (2025) 1-13."},{"key":"e_1_3_2_1_66_1","volume-title":"ChemDFM-X: towards large multimodal model for chemistry. Science China Information Sciences","author":"Zhao Zihan","year":"2024","unstructured":"Zihan Zhao, Bo Chen, Jingpiao Li, Lu Chen, Liyang Wen, Pengyu Wang, Zichen Zhu, Danyang Zhang, Yansi Li, Zhongyang Dai, Xin Chen, and Kai Yu. 2024. ChemDFM-X: towards large multimodal model for chemistry. Science China Information Sciences (2024)."},{"key":"e_1_3_2_1_67_1","unstructured":"Zihan Zhao Bo Chen Ziping Wan Lu Chen Xuanze Lin Shiyang Yu Situo Zhang Da Ma Zichen Zhu Danyang Zhang et al. 2025a. ChemDFM-R: An Chemical Reasoner LLM Enhanced with Atomized Chemical Knowledge. arXiv preprint arXiv:2507.21990 (2025)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Zihan Zhao Da Ma Lu Chen Liangtai Sun Zihao Li Yi Xia Bo Chen Hongshen Xu Zichen Zhu Su Zhu et al. 2025b. Developing ChemDFM as a large language foundation model for chemistry. Cell Reports Physical Science V6 4 (2025).","DOI":"10.1016\/j.xcrp.2025.102523"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681102"},{"key":"e_1_3_2_1_70_1","volume-title":"Benchmarking large language models for molecule prediction tasks. arXiv preprint arXiv:2403.05075","author":"Zhong Zhiqiang","year":"2024","unstructured":"Zhiqiang Zhong, Kuangyu Zhou, and Davide Mottin. 2024. Benchmarking large language models for molecule prediction tasks. arXiv preprint arXiv:2403.05075 (2024)."},{"key":"e_1_3_2_1_71_1","volume-title":"Uni-mol: A universal 3d molecular representation learning framework.","author":"Zhou Gengmo","year":"2023","unstructured":"Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. 2023. Uni-mol: A universal 3d molecular representation learning framework. (2023)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:24:47Z","timestamp":1786065887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":71,"alternative-id":["10.1145\/3770855.3818854","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818854","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}